Minor experiment fixes

examples/qed_bench.jl

@@ -44,14 +44,14 @@ if isfile(results_filename)
     df = CSV.read(results_filename, DataFrame)
 end
 
-nInputs = 2^24
+nInputs = 2^20
 
 function cpu_bench(compute_function, inputs)
     bench = @benchmark begin
         @inbounds Threads.@threads for i in eachindex($inputs)
             @invokelatest $compute_function($inputs[i])
         end
-    end gcsample = true seconds = 300
+    end gcsample = true samples = 20 evals = 1
 
     time = median(bench.times) / 1e9
     s = std(bench.times) / 1e9
@@ -67,9 +67,9 @@ function gpu_bench(kernel!, inputs)
     ts = 32
     bs = Int(n / ts)
     bench = @benchmark begin
-        @cuda threads = ts blocks = bs always_inline = true kernel!.($inputs, $outputs, $n)
+        @cuda threads = $ts blocks = $bs always_inline = true $kernel!($inputs, $outputs, $n)
         CUDA.device_synchronize()
-    end gcsample = true seconds = 300
+    end gcsample = true samples = 20 evals = 1
 
     time = median(bench.times) / 1e9
     s = std(bench.times) / 1e9
@@ -210,7 +210,7 @@ machine = Machine(
 # sadly cannot put these in functions because the world age must increase after the function is created which happens only in the global scope
 
 ## -- WARMUP TO COMPILE FUNCTIONS first
-
+#=
 optimizer = RandomWalkOptimizer(MersenneTwister(0))
 
 # 2-photon compton
@@ -230,7 +230,7 @@ opt_time = @elapsed optimize_to_fixpoint!(optimizer, graph)
 func_gen_time = @elapsed compute_func = get_compute_function(graph, process, machine)
 kernel! = get_cuda_kernel(graph, process, machine)
 bench_process(process, "warmup", graph, compute_func, kernel!, gen_time, opt_time, func_gen_time)
-
+=#
 ## -- WARMUP END
 
 optimizer = ReductionOptimizer()